Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7494b409a751d0347371ef3fc30b4add7e16c4d461399455fe430830f6c13a2f
+oid sha256:46ddd1e4610033f63b2e0bf178185383ea3c6bb041ca562c0d7cb0356317fecb
 size 267832560

run-8/checkpoint-28/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-28/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74adf2038bb2f65b777667f8200d886e2ad180bbc3d6432c7a30345896da05f4
+size 267832560

run-8/checkpoint-28/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:516cb24c6c0e318eda585f2bb9b18b394af7ad607bda479d1ab1560672e3b2b8
+size 535727290

run-8/checkpoint-28/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5633f44ec0ed7d5c4ce3563d66205768f1d52a0ca4a9c6843fa36b43565398d
+size 14308

run-8/checkpoint-28/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6395b9a0b7c29d20a109483b59c23a97fbef562eb76edccffd5ad3a9852b2fe8
+size 1064

run-8/checkpoint-28/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-28/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-28/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-14",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 28,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6572101712226868,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6768,
+      "eval_samples_per_second": 1541.101,
+      "eval_steps_per_second": 97.519,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6329525113105774,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7492,
+      "eval_samples_per_second": 1392.17,
+      "eval_steps_per_second": 88.095,
+      "step": 28
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.4691796048354265e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 21
+  }
+}

run-8/checkpoint-28/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624a7060e032d6598d3feb122ad57670da0e70d477bd73d4690f21484ec303b6
+size 4984

run-8/checkpoint-42/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-42/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1e5fbb4db6793e47ecd596d6527fa3f54413adef8b490ba569a4e23b0301ef
+size 267832560

run-8/checkpoint-42/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb7b64f54247932b871f31fd9077f23b9186918f9b55ed1dcadfee5a66738e6
+size 535727290

run-8/checkpoint-42/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2174d97f0d2ea62c7d9d153caf8368d2277b991397e454c87c13bd6252f07f54
+size 14308

run-8/checkpoint-42/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe5cb1d9d5ced6a415a9af5d3504325c7239b9008629b1b8b0ccb0223a716daa
+size 1064

run-8/checkpoint-42/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-42/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-42/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-14",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 42,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6572101712226868,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6768,
+      "eval_samples_per_second": 1541.101,
+      "eval_steps_per_second": 97.519,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6329525113105774,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7492,
+      "eval_samples_per_second": 1392.17,
+      "eval_steps_per_second": 88.095,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.621288537979126,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7495,
+      "eval_samples_per_second": 1391.575,
+      "eval_steps_per_second": 88.057,
+      "step": 42
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.4691796048354265e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 21
+  }
+}

run-8/checkpoint-42/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624a7060e032d6598d3feb122ad57670da0e70d477bd73d4690f21484ec303b6
+size 4984

run-8/checkpoint-56/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-56/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85672d3896021e2b4ccaf354a2443daa158e10667dec7c9ec6418b5eaee0f64
+size 267832560

run-8/checkpoint-56/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9db94ed5f96aa15e8c447fd737fec2227def291069e96eaf1615ffe7e41320d
+size 535727290

run-8/checkpoint-56/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4358fe6c6757720aea5b7469f89470d0cdd8c0f03a557dc907333ffda6d839b7
+size 14308

run-8/checkpoint-56/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d685b474980ab559a5b4457471e91dae7102da51f9be2c9ce121680adad9fa
+size 1064

run-8/checkpoint-56/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-56/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-56/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-14",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 56,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6572101712226868,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6768,
+      "eval_samples_per_second": 1541.101,
+      "eval_steps_per_second": 97.519,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6329525113105774,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7492,
+      "eval_samples_per_second": 1392.17,
+      "eval_steps_per_second": 88.095,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.621288537979126,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7495,
+      "eval_samples_per_second": 1391.575,
+      "eval_steps_per_second": 88.057,
+      "step": 42
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6171067953109741,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7644,
+      "eval_samples_per_second": 1364.531,
+      "eval_steps_per_second": 86.346,
+      "step": 56
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.4691796048354265e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 21
+  }
+}

run-8/checkpoint-56/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624a7060e032d6598d3feb122ad57670da0e70d477bd73d4690f21484ec303b6
+size 4984

run-8/checkpoint-70/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-8/checkpoint-70/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c455aa32725117e749f0fb6b20489ca848402174707116b761c8b8036b309b
+size 267832560

run-8/checkpoint-70/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5886fb0200073dac9fe6254f232db719482802b18a666e4134008b14df75f1dd
+size 535727290

run-8/checkpoint-70/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1504646fe540de55569afa2d0b9de66f1b0b570d1455fba9190fc4295c1e6e7b
+size 14308

run-8/checkpoint-70/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280997d2d2e08f799308c74d7b77ae5c3e6351c9c89c98064ce008c1466fdbad
+size 1064

run-8/checkpoint-70/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-70/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-70/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-14",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 70,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6572101712226868,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6768,
+      "eval_samples_per_second": 1541.101,
+      "eval_steps_per_second": 97.519,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6329525113105774,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7492,
+      "eval_samples_per_second": 1392.17,
+      "eval_steps_per_second": 88.095,
+      "step": 28
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.621288537979126,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7495,
+      "eval_samples_per_second": 1391.575,
+      "eval_steps_per_second": 88.057,
+      "step": 42
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6171067953109741,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7644,
+      "eval_samples_per_second": 1364.531,
+      "eval_steps_per_second": 86.346,
+      "step": 56
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6162344217300415,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7468,
+      "eval_samples_per_second": 1396.555,
+      "eval_steps_per_second": 88.373,
+      "step": 70
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.4691796048354265e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 21
+  }
+}

run-8/checkpoint-70/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624a7060e032d6598d3feb122ad57670da0e70d477bd73d4690f21484ec303b6
+size 4984

run-9/checkpoint-27/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-9/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ddd1e4610033f63b2e0bf178185383ea3c6bb041ca562c0d7cb0356317fecb
+size 267832560

run-9/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a30f5bd485a41b1a2eedd195d3eb36ec0310956cbb2285744ee01970e8f30ac9
+size 535727290

run-9/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee974b88ec2aa61085809c95842acad57dc0148a8c806621e48b35e8130d4f06
+size 14244

run-9/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aadcc95dde2f03e07551fe2cf0dd677d35c9261967cf41ad5d6a723f3c372618
+size 1064